{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:07:23Z","timestamp":1775200043886,"version":"3.50.1"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434724","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Can self-supervised speech models predict the perceived acceptability of prosodic variation?"],"prefix":"10.1109","author":[{"given":"Sarenne","family":"Wallbridge","sequence":"first","affiliation":[{"name":"University of Edinburgh,Centre for Speech Technology Research,UK"}]},{"given":"Adaeze","family":"Adigwe","sequence":"additional","affiliation":[{"name":"University of Edinburgh,Centre for Speech Technology Research,UK"}]},{"given":"Peter","family":"Bell","sequence":"additional","affiliation":[{"name":"University of Edinburgh,Centre for Speech Technology Research,UK"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gradience in grammar: Experimental and computational aspects of degrees of grammaticality","author":"Keller","year":"2000"},{"key":"ref2","first-page":"311","article-title":"Toward a bestiary of english intonational contours","volume-title":"The Proceedings of the North East Linguistics Society","volume":"46","author":"Goodhue"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3839.003.0016"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1658"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1002\/wcs.1579"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-19"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1250\/ast.e24.12"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2023.101577"},{"key":"ref9","first-page":"1","article-title":"can we cherry-pick?","volume-title":"IEEE International Conference on Acoustics, Speech and Signal Processing.","author":"Adigwe"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023234"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1121\/10.0026358"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2013"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746395"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0095-4470(19)30625-4"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2020-197"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2012-144"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-690"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1076"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0860"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-204"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2341"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-1771"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-339"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-438"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832295"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095710"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW62465.2024.10626267"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1121\/1.2016299"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuropsychologia.2019.107198"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-0102"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00612"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p18-1007"},{"key":"ref35","article-title":"The zero resource speech benchmark 2021: Metrics and baselines for unsupervised spoken language modeling","volume-title":"NeuRIPS Workshop on SelfSupervised Learning for Speech and Audio Processing","author":"Nguyen"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.240"},{"key":"ref37","article-title":"Natural language guidance of highfidelity text-to-speech with synthetic annotations","author":"Lyth","year":"2024","journal-title":"arXiv preprint arXiv:2402.01912"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.2307\/2334029"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-32"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Blizzard.2011-1"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273513"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref44","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","volume-title":"International Conference on Learning Representations","author":"Baevski"},{"key":"ref45","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-demo.19"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-970"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(91)90039-V"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-26"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/ssw.2019-18"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-781"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434724.pdf?arnumber=11434724","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:58:49Z","timestamp":1775192329000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434724\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434724","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}